{"id":"W6939673856","doi":"10.6084/m9.figshare.26735313.v1","title":"Additional file 1 of Beyond benchmarking and towards predictive models of dataset-specific single-cell RNA-seq pipeline performance","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Lunenfeld-Tanenbaum Research Institute; Ontario Institute for Cancer Research; University of Toronto","funders":"","keywords":"Benchmarking; Pipeline (software); Data modeling","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00002216265,0.0001232118,0.0001270727,0.0000429323,0.00003210173,0.00001818617,0.0001211093,0.0001091913,0.5003396],"category_scores_gemma":[0.00005915574,0.0001195801,0.00005469431,0.00007537489,0.0000294557,0.00001509788,0.00008335877,0.00008742137,0.000018356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008779068,"about_ca_system_score_gemma":0.00008767178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002633873,"about_ca_topic_score_gemma":0.000002735227,"domain_scores_codex":[0.9992632,0.00001300411,0.0001987103,0.000265586,0.0001324509,0.0001270206],"domain_scores_gemma":[0.9995538,0.00007771838,0.00006462754,0.0001658514,0.00009149666,0.00004650331],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003545304,0.0000522657,7.644957e-7,0.0003116691,0.00001786225,0.000002024864,0.00003159851,0.0001637496,0.02555364,0.000001081803,0.9668075,0.007022338],"study_design_scores_gemma":[0.0001848982,0.0003415745,0.00005954429,0.001286373,0.00001158565,0.000008579294,0.00001818776,0.02606972,0.09218743,0.00002409815,0.8796366,0.000171407],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.001275129,0.001208609,0.00005876279,0.000005135823,0.00004128344,0.00008848775,0.9931604,0.000008866657,0.004153322],"genre_scores_gemma":[0.1169182,0.00005446507,0.0006669302,0.00002684552,0.0002001791,0.0000576197,0.881828,0.00001676653,0.0002309674],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.5003212,"threshold_uncertainty_score":0.5001172,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0275371241649037,"score_gpt":0.2123941654024467,"score_spread":0.184857041237543,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}